Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jan 18, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K

Noise Adaptation Generative Adversarial Network for Medical Image Analysis.

Tianyang Zhang, Jun Cheng, Huazhu Fu

    IEEE Transactions on Medical Imaging
    |October 1, 2019
    PubMed
    Summary

    This study introduces a novel Noise Adaptation Generative Adversarial Network (NAGAN) to address noise variations in medical images. NAGAN effectively adapts machine learning models across different imaging devices, improving analysis outcomes without costly data relabeling.

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    DiffGeo-AOR: Diffusion-Optimized Medical Grading via Geometric Priors enhanced Autoregressive Ordinal Regression.

    IEEE transactions on medical imaging·2026
    Same author

    Real-World Insights in Designing SteatoStat: An End-to-End Deep Learning Pipeline for Hepatic Steatosis Quantification.

    Diagnostics (Basel, Switzerland)·2026
    Same author

    Annotation-efficient medical image segmentation via cross-latent graphs and vector-quantized memory.

    Medical image analysis·2026
    Same author

    STAGE challenge: Structural-Functional Transition in Glaucoma Assessment.

    Medical image analysis·2026
    Same author

    Angiography-free diagnosis of retinal diseases via interpretable multi-modal learning.

    NPJ digital medicine·2026
    Same author

    Multi-Granularity Topological Reasoning for Anatomically Consistent Vasculature Parsing.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

    Area of Science:

    • Medical Image Analysis
    • Machine Learning
    • Computer Vision

    Background:

    • Machine learning in medical imaging assumes consistent data distributions.
    • Variations in imaging devices and settings introduce noise, violating this assumption.
    • Retraining models for each new data source is expensive and time-consuming.

    Purpose of the Study:

    • To develop a noise adaptation method for medical images.
    • To enable the use of pre-trained models on new data with different noise characteristics.
    • To overcome limitations of current machine learning models in handling diverse medical image noise.

    Main Methods:

    • Reformulated noise adaptation as an image-to-image translation problem.
    • Proposed a novel Noise Adaptation Generative Adversarial Network (NAGAN).

    Related Experiment Videos

    Last Updated: Jan 18, 2026

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    3.3K
  • NAGAN utilizes a generator and two discriminators to match noise patterns and preserve content.

    • Main Results:

    • NAGAN successfully translated noise styles in optical coherence tomography (OCT) and ultrasound images.
    • The method demonstrated improved segmentation in OCT and classification in ultrasound tasks.
    • Experimental results validate the effectiveness of NAGAN in improving medical image analysis outcomes.

    Conclusions:

    • NAGAN offers an effective solution for noise adaptation in medical imaging.
    • The proposed method enhances the generalizability of machine learning models across different data sources.
    • This approach reduces the need for extensive data labeling and model retraining.